locuslab / ase
Analogous Safe-state Exploration (ASE) is an algorithm for provably safe and optimal exploration in MDPs with unknown, stochastic dynamics.
☆11Updated 3 years ago
Alternatives and similar repositories for ase:
Users that are interested in ase are comparing it to the libraries listed below
- TaskMet Task-driven Metric Learning for Model Learning☆18Updated 11 months ago
- Deep reinforcement learning for adaptation in evolutionary algorithms☆9Updated 5 years ago
- codes for TokenManipulationGAN☆7Updated 4 years ago
- 🤖 Implementation of Self Normalizing Networks (SNN) in PyTorch.☆12Updated 7 years ago
- simple reinforcement learning example for the minecraft☆9Updated 6 years ago
- Understanding RL vision Distill article☆23Updated last year
- NeurIPS 2019 Paper Implementation☆12Updated 2 years ago
- Investigate the speed of adaptation of structural causal models☆16Updated 3 years ago
- Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematics (AAAI 2022)☆14Updated 2 years ago
- Code for Unbiased Implicit Variational Inference (UIVI)☆13Updated 6 years ago
- A framework for implementing equivariant DL☆10Updated 3 years ago
- Quasi-Newton Algorithm for Stochastic Optimization☆10Updated 2 years ago
- Reference implementation of algorithms for reinforcement learning and Markov decision processes.☆11Updated 3 years ago
- Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch☆23Updated 4 years ago
- Code for our ICLR Trustworthy ML 2020 workshop paper "Improved Image Wasserstein Attacks and Defenses"☆14Updated 4 years ago
- Variational Walkback, NIPS'17☆28Updated 7 years ago
- Variable-order CRFs with structure learning☆16Updated 5 months ago
- Implementation of the LOSSGRAD optimization algorithm☆15Updated 5 years ago
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Updated last year
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆14Updated 3 years ago
- ☆12Updated 2 years ago
- Code for "MIM: Mutual Information Machine" paper.☆16Updated 2 years ago
- Automatically generate simple meta-learning tasks from a very large space☆15Updated last year
- Official repository for the paper "Goal-Conditioned Generators of Deep Policies"☆11Updated 2 years ago
- ☆14Updated 5 years ago
- ☆12Updated 4 years ago
- ☆14Updated last year
- Fast IdEntification of State-of-The-Art models using adaptive bandit algorithms☆14Updated 2 years ago